遥感图像分类方法评析与展望

Expectation and Evaluation of the Methods on RemoteSensing Image Classifications

从遥感图像分类的基本概念和特征出发,在对各算法进行划分基础上,分析评价了主要遥感图像分类方法的原理、特点,优势与限制,并阐明了各主要方法作用及其意义,指出目前存在的问题,展望了遥感图像分类方法的发展与应用前景。

This paper is based on the concept and characteristic of Remote Sensing classifications, combining the predecessors' fruits, then sums up all the methods (including traditional and new classifications, such as: object-oriented, sub-pixel classification etc.), detailed analyzes and evaluates each of them. Afterwards, it attempts to analyze the methods and the arithmetic of classifications, such as principles, effects, functions and limited conditions. It also compares the excellence, the defects and adapting conditions of each method, and summarizes all of the methods in different views. Finally, summary and prospect are described, in order to give guidance to practical work.